Metraipolis › archive › dc_bf24b22daba0

Accelerating posterior sampling in Bayesian inverse problems with diffusion models: an online-offline perspective — arXiv:2611.01300

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01300
License (as archived)
CC0-1.0
Archived
2026-11-03T18:36:47.169Z
SHA-256 of the archived text
77fc58e5f544aec679bade2f3f3e9ef5e08367c3f26508855e8f06ffab568854
Stable URL of this page
https://metraipolis.com/documento/dc_bf24b22daba0

How to cite

Accelerating posterior sampling in Bayesian inverse problems with diffusion models: an online-offline perspective — arXiv:2611.01300 — arXiv (en), https://arxiv.org/abs/2611.01300 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf24b22daba0 (Metraipolis archive dc_bf24b22daba0, sha256 77fc58e5f544aec679bade2f3f3e9ef5e08367c3f26508855e8f06ffab568854)
BibTeX
@misc{dcbf24b22daba0,
  title = {Accelerating posterior sampling in Bayesian inverse problems with diffusion models: an online-offline perspective — arXiv:2611.01300},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01300},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf24b22daba0; sha256 77fc58e5f544aec679bade2f3f3e9ef5e08367c3f26508855e8f06ffab568854},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01300. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Bayesian inverse problems require both informative prior models and computationally feasible posterior inference. Score-based diffusion models provide expressive learned priors, but their use for inversion introduces a conditioning problem: the score of a noised posterior is generally unavailable from a prior score alone. This selective survey reviews the principal approaches to that problem, including likelihood guidance, spectral and projection methods, sequential Monte Carlo corrections, and amortized conditional training. We organize methods by how they split cost between offline preparation and online inference, and compare their assumptions, advantages and limitations, with emphasis on computational speedups. Some ongoing directions and open questions are gathered at the end.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Numerical Analysis (math.NA); Statistics Theory (math.ST); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.01300 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:12:54.486Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).